> ## Documentation Index > Fetch the complete documentation index at: https://doc.lucidworks.com/llms.txt > Use this file to discover all available pages before exploring further. # Passthrough use case > The passthrough use case lets you use the service as a proxy to the large language model (LLM). The service sends text (no additional prompts or other information) to the LLM. The POST request obtains and indexes prediction information related to the specified use case, and returns a unique `predictionId` and `status` of the request. The `predictionId` can be used later in the GET request to retrieve the results. ## OpenAPI ````yaml /api-reference/saas/machine-learning-platform-async-prediction.json post /ai/async-prediction/passthrough/{MODEL_ID} openapi: 3.0.1 info: title: Lucidworks AI Async Prediction API version: v0 description: >- The Lucidworks AI Async Prediction API contains two requests: * POST Request: This request is used to submit a prediction task for a specific `useCase` and `modelId`. Upon submission, the API responds with the following information: * `predictionId` that is a unique UUID for the submitted prediction task, and can be used later to retrieve the results. * `status` that indicates the current state of the prediction task. * GET Request: This request is used to retrieve the results of a previously-submitted prediction request. You must provide the unique `predictionId` received from the POST request. The API then returns the results of the prediction request associated with that `predictionId`. The Use Case API returns a list of all supported models. The `async-prediction` endpoints require an authentication token with scope `machinelearning.predict`. contact: name: Lucidworks url: https://lucidworks.com/ email: support@lucidworks.com termsOfService: https://lucidworks.com/legal/developer-license-agreement/ license: name: Lucidworks url: https://lucidworks.com/legal/developer-license-agreement/ servers: - url: https://APPLICATION_ID.applications.lucidworks.com description: Production security: [] tags: - name: Create predictions description: Submit prediction tasks to Lucidworks AI. - name: Fetch predictions description: Get the results of a prediction task from Lucidworks AI. paths: /ai/async-prediction/passthrough/{MODEL_ID}: parameters: - schema: type: string name: MODEL_ID in: path required: true description: Unique identifier for the model. example: llama-3-8b-instruct post: tags: - Create predictions summary: Passthrough use case description: >- The passthrough use case lets you use the service as a proxy to the large language model (LLM). The service sends text (no additional prompts or other information) to the LLM. The POST request obtains and indexes prediction information related to the specified use case, and returns a unique `predictionId` and `status` of the request. The `predictionId` can be used later in the GET request to retrieve the results. operationId: post-ai-async-prediction-passthrough-modelId parameters: - in: header name: Authorization schema: type: string required: true description: >- Bearer token used for authentication. Format: `Authorization: Bearer ACCESS_TOKEN`. example: Bearer abc123def456 - schema: type: string example: application/json in: header name: Content-Type description: application/json requestBody: content: application/json: schema: $ref: '#/components/schemas/PassthroughRequest' example: batch: - text: >- [{"role": "system", "content": "You are a helpful utility program instructed to accomplish a word correction task. Provide the most likely suggestion to the user without a preamble or elaboration."}, {"role": "user", "content": "misspeled"}, {"role": "assistant", "content": "CORRECT:"}] useCaseConfig: dataType: json_prompt responses: '200': description: OK content: application/json: schema: $ref: '#/components/schemas/POSTresponse' example: predictionId: 5e893b16-01f8-427c-9ca8-ba52b01b1ba3 status: SUBMITTED 4XX: $ref: '#/components/responses/Error' components: schemas: PassthroughRequest: title: PassthroughRequest type: object x-examples: {} properties: batch: type: array description: >- The batch of key:value pairs used as inputs in the prediction. Up to 32 inputs per request are allowed. maxItems: 32 items: type: object properties: text: type: string description: The content the model analyzes. example: >- [{\"role\": \"system\", \"content\": \"You are a helpful utility program instructed to accomplish a word correction task. Provide the most likely suggestion to the user without an preamble or elaboration.\"}, {\"role\": \"user\", \"content\": \"misspeled\"}, {\"role\": \"assistant\", \"content\": \"CORRECT:\"}] useCaseConfig: $ref: '#/components/schemas/UseCaseConfigPassthrough' modelConfig: $ref: '#/components/schemas/ModelConfig' POSTresponse: title: POST response type: object description: >- This is the response to the POST prediction request submitted for a specific `useCase` and `modelId`. properties: predictionId: type: string format: uuid description: >- The universal unique identifier (UUID) returned in the POST request. This UUID is required in the GET request to retrieve results. status: type: string example: SUBMITTED description: >- The current status of the prediction. Allowed values are: * SUBMITTED - The POST request was successful and the response has returned the `predictionId` and `status` that is used by the GET request. * ERROR - An error was generated when the GET request was sent. * READY - The results associated with the `predictionId` are available and ready to be retrieved. * RETRIEVED - The results associated with the `predictionId` are returned successfully when the GET request was sent. UseCaseConfigPassthrough: title: UseCaseConfigPassthrough type: object properties: useSystemPrompt: type: boolean description: >- This optional parameter contains a default value of true. If set to false, the `batch.text` value serves as the prompt for the model. The prompt must be in a specific format the model can comprehend. dataType: type: string description: >- This optional parameter enables model-specific handling in the Prediction API to help improve model accuracy. Use the most applicable fields based on available dataTypes and the dataType value that best aligns with the text sent to the Prediction API. The values for `dataType` in the Passthrough use case are: * `"dataType": "text"` - This value is equivalent to `"useSystemPrompt": true` and is a pre-defined, generic prompt. * `"dataType": "raw_prompt"` - This value is equivalent to `"useSystemPrompt": false` and is passed directly to the model or third-party API. * `"dataType": "json_prompt"` - This value follows the generics that allow three roles: - `system` - `user` - Only the last user message is truncated. - If the API does not support system prompts, the user role is substituted for the system role. - `assistant` - If the last message role is `assistant`, it is used as a pre-fill for generation and is the first generated token the model uses. The pre-fill is prepended to the model output, which makes models less verbose and helps enforce specific outputs such as YAML. - The Google Vertex AI does not support generation pre-fills, so an exception error is generated. - This follows the HuggingFace template contraints at https://huggingface.co/docs/transformers/main/en/chat_templating. - Additional `json_prompt` information: - Consecutive messages for the same role are merged. - You can paste the information for a hosted model into the `json_prompt` value and change the model name in the stage. example: text ModelConfig: title: ModelConfig type: object description: >- Provides fields and values that specify ranges for tokens. Fields used for specific use cases and models are specified. The default values are used if other values are not specified. properties: temperature: type: number format: float example: 0.8 minimum: 0 maximum: 2 description: >- A sampling temperature between 0 and 2. A higher sampling temperature such as 0.8, results in more random (creative) output. A lower value such as 0.2 results in more focused (conservative) output. A lower value does not guarantee the model returns the same response for the same input. We recommend staying at or below a temperature of 1.0. Values above 1.0 might return nonsense unless the topP value is lowered to be more deterministic. topP: type: number format: float example: 1 minimum: 1 maximum: 1 description: >- A floating-point number that controls the cumulative probability of the top tokens to consider. Required range is [0, 1]. Set topP to 1 to consider all tokens. topK: type: integer example: -1 description: >- An integer that controls the number of top tokens to consider. Set topK to -1 to consider all tokens. presencePenalty: type: number format: float minimum: -2 maximum: 2 description: >- A floating-point number that penalizes new tokens based on whether they have already appeared in the text. Required range is [-2, 2]. A value greater than zero (0) encourages the model to use new tokens. A value less than zero (0) encourages the model to repeat existing tokens. This is applicable for all OpenAI and Llama models. example: 2 frequencyPenalty: type: number format: float minimum: -2 maximum: 2 example: 1 description: >- A floating-point number that penalizes new tokens based on their frequency in the generated text. Required range is [-2, 2]. A value greater than zero (0) encourages the model to use new tokens. A value less than zero (0) encourages the model to repeat existing tokens. This is applicable for all OpenAI and Llama models. maxTokens: type: integer format: int32 example: 1 description: The maximum number of tokens to generate per output sequence. apiKey: type: string description: >- This optional parameter is only required when using the model for prediction. You can find this value in your model's settings: * **OpenAI**: Copy and paste the API key found in your organization's settings. For more information, see OpenAI Authentication API keys. * **Azure OpenAI**: Copy and paste the API key found in your Azure portal. See Authenticate with API key. * **Anthropic**: Copy and paste the API key found in your Anthropic console or by using the Anthropic API. * **Google Vertex AI**: Copy and paste the base64-encoded service account key JSON found in your Google Cloud console. This service account key must have the Vertex AI user role enabled. For more information, see generate service account key. example: API key specific to use case and model azureDeployment: type: string description: >- This optional parameter is the name of the deployed Azure OpenAI model and is only required when a deployed Azure OpenAI model is used for prediction. example: DEPLOYMENT_NAME azureEndpoint: type: string description: >- This optional parameter is the URL endpoint of the deployed Azure OpenAI model and is only required when a deployed Azure OpenAI model is used for prediction. example: https://azure.endpoint.com googleProjectId: type: string example: '[GOOGLE_PROJECT_ID]' description: >- This parameter is optional, and is only required when a Google Vertex AI model is used for prediction. googleRegion: type: string description: >- This parameter is optional, and is only required when a Google Vertex AI model is used for prediction. A value of `global` routes the query to any available region. Other possible region values are: * us-central1 * us-west4 * northamerica-northeast1 * us-east4 * us-west1 * asia-northeast3 * asia-southeast1 * asia-northeast example: '[GOOGLE_PROJECT_REGION_OF_MODEL_ACCESS]' predictionId: title: predictionId type: string description: >- The universal unique identifier (UUID) returned in the POST request. This UUID is required in the GET request to retrieve results. format: uuid example: fd110486-f168-47c0-a419-1518a4840589 status: title: status type: string description: >- The current status of the prediction. Allowed values are: * `SUBMITTED` - The POST request was successful and the response has returned the `predictionId` and `status` that is used by the GET request. * `READY` - The results associated with the `predictionId` are available and ready to be retrieved. * `ERROR` - An error was generated when the GET request was sent. * `RETRIEVED` - The results associated with the `predictionId` are returned successfully when the GET request was sent. example: READY responses: Error: description: >- The error varies based on the issue encountered regarding the `predictionId` or related information. content: application/json: schema: type: object properties: predictionId: $ref: '#/components/schemas/predictionId' status: $ref: '#/components/schemas/status' message: type: string description: >- The error generated if the `predictionId` cannot be located or the related information cannot be retrieved. For example, "System prompt exceeded the maximum number of allowed input tokens." ````